Skip to content
Monopea

Monopea Agent flows

Design the team, not just the prompt.

A canvas for per-project agent teams: who runs, who supervises, and what each one may read. Every sub-agent inherits the same gate, and a stop cascades to everything it delegated.

Start freeSee pricing
supervisoryou asked for 4analystfolders: data/writerfolders: drafts/reviewerfolders: drafts/financefolders: ledger/fan-in · one answersame gate for every agent

—

No proprietary file format

7

Agent tools behind this app

1

Approval gate for every outward action

CH · EU

Stored in Switzerland. Processed in the EU.

The Agent flows canvas, showing three research agents feeding a supervisor that hands off to a drafting agent, each card naming the persona it runs, the tools it may call and the single folder it is allowed to read.
Agent flows · three agents into a supervisor, each with the one folder it may read

What you ask → what actually happens

Agent flows, in the words people type.

Mechanism, not adjectives: each line is what the agent does when you say it.

“Do these four at once.”

Fans the work out to sub-agents — because you asked; it does not decide to multiply itself.

“Have the reviewer check the analyst’s work.”

A supervisor collects the results and fans them back in.

“Stop everything.”

The stop cascades to every agent the run delegated; completed work is kept and logged.

Capabilities

What Agent flows does.

01

A canvas for the team

Per-project agent teams, drawn rather than scripted.

02

Supervisor fan-in

One agent collects and checks what the others produced.

03

Folder permissions

Per-agent access to your documents.

04

Inherited gate

Every sub-agent is held to the same approval threshold as the one that spawned it.

Tools the agent calls

Real functions, not a chat reply.

Verbatim names from the runtime catalog. Every call is logged; anything outward is a proposal first.

  • orchestrate__delegate
  • orchestrate__ask_agent
  • orchestrate__send_to_agent
  • orchestrate__stop_agent
  • orchestrate__list_jobs
  • orchestrate__schedule_action
  • orchestrate__respawn_from

Governed

It works on its own. It asks at the door.

Inside the workspace the agent just works. Anything above the one risk threshold you set — and anything that leaves — becomes a proposal with its exact arguments, and waits for you.

How the approval gate works
Proposal · send renewal quotedrafted in the workspacecredentials by {{secret}} onlyabove your threshold → askwaiting…Approveactivity logdispatched

Works with

The rest of the suite, one agent.

Teams

Members, roles and per-project scope, and agent personas with their own brief — the agent can run the workspace admin it is authorised for, and changes to who sees what are proposals.

Explore Teams

Catalog

Connect any MCP-compatible server, or build a tool library from API documentation. New tools start needing approval, and credentials are referenced as {{secret:NAME}} — never shown to the model.

Explore Catalog

Library

Files, long-term memory and a knowledge graph the agent builds as it reads — consulted on every turn, with the evidence behind an answer graded so you can see how well-supported it is.

Explore Library

FAQ

Agent flows, answered.

Will it spawn sub-agents on its own?
No. Delegation is explicit — a run fans out because you asked it to.
Can I stop a whole team?
Yes. Stopping a run cascades to everything it delegated; work already completed is preserved and logged.
Does the agent need my approval for everything?
No — that would make it a form, not an agent. Work inside the workspace runs on its own; anything above the one risk threshold you set, and anything that leaves the workspace, becomes a proposal with its exact arguments and waits for you.

Hand Agent flows its first job.

Open a workspace, give the agent a task, and approve what it proposes. Stored in Switzerland, processed in the EU.

Start freeSee every product